1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
|
/*
* Copyright (C) 2006 George Staikos <staikos@kde.org>
* Copyright (C) 2006 Alexey Proskuryakov <ap@nypop.com>
* Copyright (C) 2007 Apple Computer, Inc. All rights reserved.
* Copyright (C) 2007-2009 Torch Mobile, Inc.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Library General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Library General Public License for more details.
*
* You should have received a copy of the GNU Library General Public License
* along with this library; see the file COPYING.LIB. If not, write to
* the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
* Boston, MA 02110-1301, USA.
*
*/
#ifndef WTF_UnicodeWinCE_h
#define WTF_UnicodeWinCE_h
#include "UnicodeMacrosFromICU.h"
#include "ce_unicode.h"
#define TO_MASK(x) (1 << (x))
namespace WTF {
namespace Unicode {
enum Direction {
LeftToRight = UnicodeCE::U_LEFT_TO_RIGHT,
RightToLeft = UnicodeCE::U_RIGHT_TO_LEFT,
EuropeanNumber = UnicodeCE::U_EUROPEAN_NUMBER,
EuropeanNumberSeparator = UnicodeCE::U_EUROPEAN_NUMBER_SEPARATOR,
EuropeanNumberTerminator = UnicodeCE::U_EUROPEAN_NUMBER_TERMINATOR,
ArabicNumber = UnicodeCE::U_ARABIC_NUMBER,
CommonNumberSeparator = UnicodeCE::U_COMMON_NUMBER_SEPARATOR,
BlockSeparator = UnicodeCE::U_BLOCK_SEPARATOR,
SegmentSeparator = UnicodeCE::U_SEGMENT_SEPARATOR,
WhiteSpaceNeutral = UnicodeCE::U_WHITE_SPACE_NEUTRAL,
OtherNeutral = UnicodeCE::U_OTHER_NEUTRAL,
LeftToRightEmbedding = UnicodeCE::U_LEFT_TO_RIGHT_EMBEDDING,
LeftToRightOverride = UnicodeCE::U_LEFT_TO_RIGHT_OVERRIDE,
RightToLeftArabic = UnicodeCE::U_RIGHT_TO_LEFT_ARABIC,
RightToLeftEmbedding = UnicodeCE::U_RIGHT_TO_LEFT_EMBEDDING,
RightToLeftOverride = UnicodeCE::U_RIGHT_TO_LEFT_OVERRIDE,
PopDirectionalFormat = UnicodeCE::U_POP_DIRECTIONAL_FORMAT,
NonSpacingMark = UnicodeCE::U_DIR_NON_SPACING_MARK,
BoundaryNeutral = UnicodeCE::U_BOUNDARY_NEUTRAL
};
enum DecompositionType {
DecompositionNone = UnicodeCE::U_DT_NONE,
DecompositionCanonical = UnicodeCE::U_DT_CANONICAL,
DecompositionCompat = UnicodeCE::U_DT_COMPAT,
DecompositionCircle = UnicodeCE::U_DT_CIRCLE,
DecompositionFinal = UnicodeCE::U_DT_FINAL,
DecompositionFont = UnicodeCE::U_DT_FONT,
DecompositionFraction = UnicodeCE::U_DT_FRACTION,
DecompositionInitial = UnicodeCE::U_DT_INITIAL,
DecompositionIsolated = UnicodeCE::U_DT_ISOLATED,
DecompositionMedial = UnicodeCE::U_DT_MEDIAL,
DecompositionNarrow = UnicodeCE::U_DT_NARROW,
DecompositionNoBreak = UnicodeCE::U_DT_NOBREAK,
DecompositionSmall = UnicodeCE::U_DT_SMALL,
DecompositionSquare = UnicodeCE::U_DT_SQUARE,
DecompositionSub = UnicodeCE::U_DT_SUB,
DecompositionSuper = UnicodeCE::U_DT_SUPER,
DecompositionVertical = UnicodeCE::U_DT_VERTICAL,
DecompositionWide = UnicodeCE::U_DT_WIDE,
};
enum CharCategory {
NoCategory = 0,
Other_NotAssigned = TO_MASK(UnicodeCE::U_GENERAL_OTHER_TYPES),
Letter_Uppercase = TO_MASK(UnicodeCE::U_UPPERCASE_LETTER),
Letter_Lowercase = TO_MASK(UnicodeCE::U_LOWERCASE_LETTER),
Letter_Titlecase = TO_MASK(UnicodeCE::U_TITLECASE_LETTER),
Letter_Modifier = TO_MASK(UnicodeCE::U_MODIFIER_LETTER),
Letter_Other = TO_MASK(UnicodeCE::U_OTHER_LETTER),
Mark_NonSpacing = TO_MASK(UnicodeCE::U_NON_SPACING_MARK),
Mark_Enclosing = TO_MASK(UnicodeCE::U_ENCLOSING_MARK),
Mark_SpacingCombining = TO_MASK(UnicodeCE::U_COMBINING_SPACING_MARK),
Number_DecimalDigit = TO_MASK(UnicodeCE::U_DECIMAL_DIGIT_NUMBER),
Number_Letter = TO_MASK(UnicodeCE::U_LETTER_NUMBER),
Number_Other = TO_MASK(UnicodeCE::U_OTHER_NUMBER),
Separator_Space = TO_MASK(UnicodeCE::U_SPACE_SEPARATOR),
Separator_Line = TO_MASK(UnicodeCE::U_LINE_SEPARATOR),
Separator_Paragraph = TO_MASK(UnicodeCE::U_PARAGRAPH_SEPARATOR),
Other_Control = TO_MASK(UnicodeCE::U_CONTROL_CHAR),
Other_Format = TO_MASK(UnicodeCE::U_FORMAT_CHAR),
Other_PrivateUse = TO_MASK(UnicodeCE::U_PRIVATE_USE_CHAR),
Other_Surrogate = TO_MASK(UnicodeCE::U_SURROGATE),
Punctuation_Dash = TO_MASK(UnicodeCE::U_DASH_PUNCTUATION),
Punctuation_Open = TO_MASK(UnicodeCE::U_START_PUNCTUATION),
Punctuation_Close = TO_MASK(UnicodeCE::U_END_PUNCTUATION),
Punctuation_Connector = TO_MASK(UnicodeCE::U_CONNECTOR_PUNCTUATION),
Punctuation_Other = TO_MASK(UnicodeCE::U_OTHER_PUNCTUATION),
Symbol_Math = TO_MASK(UnicodeCE::U_MATH_SYMBOL),
Symbol_Currency = TO_MASK(UnicodeCE::U_CURRENCY_SYMBOL),
Symbol_Modifier = TO_MASK(UnicodeCE::U_MODIFIER_SYMBOL),
Symbol_Other = TO_MASK(UnicodeCE::U_OTHER_SYMBOL),
Punctuation_InitialQuote = TO_MASK(UnicodeCE::U_INITIAL_PUNCTUATION),
Punctuation_FinalQuote = TO_MASK(UnicodeCE::U_FINAL_PUNCTUATION)
};
CharCategory category(unsigned int);
bool isSpace(wchar_t);
bool isLetter(wchar_t);
bool isPrintableChar(wchar_t);
bool isUpper(wchar_t);
bool isLower(wchar_t);
bool isPunct(wchar_t);
bool isDigit(wchar_t);
bool isAlphanumeric(wchar_t);
inline bool isSeparatorSpace(wchar_t c) { return category(c) == Separator_Space; }
inline bool isHighSurrogate(wchar_t c) { return (c & 0xfc00) == 0xd800; }
inline bool isLowSurrogate(wchar_t c) { return (c & 0xfc00) == 0xdc00; }
wchar_t toLower(wchar_t);
wchar_t toUpper(wchar_t);
wchar_t foldCase(wchar_t);
wchar_t toTitleCase(wchar_t);
int toLower(wchar_t* result, int resultLength, const wchar_t* source, int sourceLength, bool* isError);
int toUpper(wchar_t* result, int resultLength, const wchar_t* source, int sourceLength, bool* isError);
int foldCase(UChar* result, int resultLength, const wchar_t* source, int sourceLength, bool* isError);
int digitValue(wchar_t);
wchar_t mirroredChar(UChar32);
unsigned char combiningClass(UChar32);
DecompositionType decompositionType(UChar32);
Direction direction(UChar32);
inline bool isArabicChar(UChar32 c)
{
return c >= 0x0600 && c <= 0x06FF;
}
inline bool hasLineBreakingPropertyComplexContext(UChar32)
{
return false; // FIXME: implement!
}
inline int umemcasecmp(const wchar_t* a, const wchar_t* b, int len)
{
for (int i = 0; i < len; ++i) {
wchar_t c1 = foldCase(a[i]);
wchar_t c2 = foldCase(b[i]);
if (c1 != c2)
return c1 - c2;
}
return 0;
}
inline UChar32 surrogateToUcs4(wchar_t high, wchar_t low)
{
return (UChar32(high) << 10) + low - 0x35fdc00;
}
} // namespace Unicode
} // namespace WTF
#endif // WTF_UnicodeWinCE_h
|
